© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 168639
    Prev
    Next
    INDEX
    Explanations

    staff and personnel

    np_acts-logits-general · gemini-2.5-flash-lite

    treated by staff

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     semblent
    0.51
    ນ
    0.46
     toute
    0.46
     sudut
    0.46
     veux
    0.45
     plugging
    0.45
    がいい
    0.45
     ଭ
    0.45
    elfalt
    0.45
     bolted
    0.44
    POSITIVE LOGITS
    RELATIVA
    0.43
     clergy
    0.43
     personnel
    0.42
    elli
    0.42
    職員
    0.42
    Residence
    0.41
     Staff
    0.41
     Cabinet
    0.41
    larının
    0.41
    BANK
    0.41
    Activations Density 0.001%

    No Known Activations